Hugging Face's logo

prithivMLmods
/
Human-Action-Recognition

Image Classification
Transformers
Safetensors
English
siglip
Human-Action-Recognition
Model card Files
xet
Community
prithivMLmods commited on
Commit
a62c5d4
·
verified ·
1 Parent(s): 4ce5366

Upload folder using huggingface_hub

Browse files
Files changed (20) hide show
  1. checkpoint-394/config.json +72 -0
  2. checkpoint-394/model.safetensors +3 -0
  3. checkpoint-394/optimizer.pt +3 -0
  4. checkpoint-394/preprocessor_config.json +24 -0
  5. checkpoint-394/rng_state.pth +3 -0
  6. checkpoint-394/scheduler.pt +3 -0
  7. checkpoint-394/trainer_state.json +44 -0
  8. checkpoint-394/training_args.bin +3 -0
  9. checkpoint-788/config.json +72 -0
  10. checkpoint-788/model.safetensors +3 -0
  11. checkpoint-788/optimizer.pt +3 -0
  12. checkpoint-788/preprocessor_config.json +24 -0
  13. checkpoint-788/rng_state.pth +3 -0
  14. checkpoint-788/scheduler.pt +3 -0
  15. checkpoint-788/trainer_state.json +61 -0
  16. checkpoint-788/training_args.bin +3 -0
  17. config.json +72 -0
  18. model.safetensors +3 -0
  19. preprocessor_config.json +24 -0
  20. training_args.bin +3 -0
checkpoint-394/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "calling",
7
+ "1": "clapping",
8
+ "2": "cycling",
9
+ "3": "dancing",
10
+ "4": "drinking",
11
+ "5": "eating",
12
+ "6": "fighting",
13
+ "7": "hugging",
14
+ "8": "laughing",
15
+ "9": "listening_to_music",
16
+ "10": "running",
17
+ "11": "sitting",
18
+ "12": "sleeping",
19
+ "13": "texting",
20
+ "14": "using_laptop"
21
+ },
22
+ "initializer_factor": 1.0,
23
+ "label2id": {
24
+ "calling": 0,
25
+ "clapping": 1,
26
+ "cycling": 2,
27
+ "dancing": 3,
28
+ "drinking": 4,
29
+ "eating": 5,
30
+ "fighting": 6,
31
+ "hugging": 7,
32
+ "laughing": 8,
33
+ "listening_to_music": 9,
34
+ "running": 10,
35
+ "sitting": 11,
36
+ "sleeping": 12,
37
+ "texting": 13,
38
+ "using_laptop": 14
39
+ },
40
+ "model_type": "siglip",
41
+ "problem_type": "single_label_classification",
42
+ "text_config": {
43
+ "attention_dropout": 0.0,
44
+ "hidden_act": "gelu_pytorch_tanh",
45
+ "hidden_size": 768,
46
+ "intermediate_size": 3072,
47
+ "layer_norm_eps": 1e-06,
48
+ "max_position_embeddings": 64,
49
+ "model_type": "siglip_text_model",
50
+ "num_attention_heads": 12,
51
+ "num_hidden_layers": 12,
52
+ "projection_size": 768,
53
+ "torch_dtype": "float32",
54
+ "vocab_size": 256000
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "vision_config": {
59
+ "attention_dropout": 0.0,
60
+ "hidden_act": "gelu_pytorch_tanh",
61
+ "hidden_size": 768,
62
+ "image_size": 224,
63
+ "intermediate_size": 3072,
64
+ "layer_norm_eps": 1e-06,
65
+ "model_type": "siglip_vision_model",
66
+ "num_attention_heads": 12,
67
+ "num_channels": 3,
68
+ "num_hidden_layers": 12,
69
+ "patch_size": 16,
70
+ "torch_dtype": "float32"
71
+ }
72
+ }
checkpoint-394/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963d9aad1de24abafe6f040f6f8c0768b255a85adaa801f948ceaaccd126a037
3
+ size 371607988
checkpoint-394/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bd85ca6992cfc002f42375a1f2772a60bc0c2dbbab23b2936bd8b7a8fbfb2af
3
+ size 686635642
checkpoint-394/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
checkpoint-394/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2fd0a07af4e598faf1b0498ac2b426fba5ce895c882babe0299e3c379d9055a
3
+ size 14244
checkpoint-394/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87e8e5a6ae9f04fa1e5bcb9d293d1c2099daad36430ebd172bbcc5b39dbbc977
3
+ size 1064
checkpoint-394/trainer_state.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 394,
3
+ "best_metric": 0.9223098158836365,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-394",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 394,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.788968253968254,
15
+ "eval_loss": 0.9223098158836365,
16
+ "eval_model_preparation_time": 0.007,
17
+ "eval_runtime": 160.6375,
18
+ "eval_samples_per_second": 78.437,
19
+ "eval_steps_per_second": 9.805,
20
+ "step": 394
21
+ }
22
+ ],
23
+ "logging_steps": 500,
24
+ "max_steps": 788,
25
+ "num_input_tokens_seen": 0,
26
+ "num_train_epochs": 2,
27
+ "save_steps": 500,
28
+ "stateful_callbacks": {
29
+ "TrainerControl": {
30
+ "args": {
31
+ "should_epoch_stop": false,
32
+ "should_evaluate": false,
33
+ "should_log": false,
34
+ "should_save": true,
35
+ "should_training_stop": false
36
+ },
37
+ "attributes": {}
38
+ }
39
+ },
40
+ "total_flos": 1.0554330123767808e+18,
41
+ "train_batch_size": 32,
42
+ "trial_name": null,
43
+ "trial_params": null
44
+ }
checkpoint-394/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6accd8d14522454c70031a1ac819cad32d4e338136bd21a2a4dcb3fdb03364bb
3
+ size 5304
checkpoint-788/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "calling",
7
+ "1": "clapping",
8
+ "2": "cycling",
9
+ "3": "dancing",
10
+ "4": "drinking",
11
+ "5": "eating",
12
+ "6": "fighting",
13
+ "7": "hugging",
14
+ "8": "laughing",
15
+ "9": "listening_to_music",
16
+ "10": "running",
17
+ "11": "sitting",
18
+ "12": "sleeping",
19
+ "13": "texting",
20
+ "14": "using_laptop"
21
+ },
22
+ "initializer_factor": 1.0,
23
+ "label2id": {
24
+ "calling": 0,
25
+ "clapping": 1,
26
+ "cycling": 2,
27
+ "dancing": 3,
28
+ "drinking": 4,
29
+ "eating": 5,
30
+ "fighting": 6,
31
+ "hugging": 7,
32
+ "laughing": 8,
33
+ "listening_to_music": 9,
34
+ "running": 10,
35
+ "sitting": 11,
36
+ "sleeping": 12,
37
+ "texting": 13,
38
+ "using_laptop": 14
39
+ },
40
+ "model_type": "siglip",
41
+ "problem_type": "single_label_classification",
42
+ "text_config": {
43
+ "attention_dropout": 0.0,
44
+ "hidden_act": "gelu_pytorch_tanh",
45
+ "hidden_size": 768,
46
+ "intermediate_size": 3072,
47
+ "layer_norm_eps": 1e-06,
48
+ "max_position_embeddings": 64,
49
+ "model_type": "siglip_text_model",
50
+ "num_attention_heads": 12,
51
+ "num_hidden_layers": 12,
52
+ "projection_size": 768,
53
+ "torch_dtype": "float32",
54
+ "vocab_size": 256000
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "vision_config": {
59
+ "attention_dropout": 0.0,
60
+ "hidden_act": "gelu_pytorch_tanh",
61
+ "hidden_size": 768,
62
+ "image_size": 224,
63
+ "intermediate_size": 3072,
64
+ "layer_norm_eps": 1e-06,
65
+ "model_type": "siglip_vision_model",
66
+ "num_attention_heads": 12,
67
+ "num_channels": 3,
68
+ "num_hidden_layers": 12,
69
+ "patch_size": 16,
70
+ "torch_dtype": "float32"
71
+ }
72
+ }
checkpoint-788/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2b9d5be40e7e84d93cbe40bf0b2b67d36503aa45faab3593811c712c53f649
3
+ size 371607988
checkpoint-788/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d33b0e2623ab06cc9c534c4d8f8927dc36ff577301e041ec7bd03a7722ac59
3
+ size 686635642
checkpoint-788/preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
checkpoint-788/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a8a83a026ed4118366d4ed2f53eb9b0482a9f032c9de4d7e53cc37f5699cbc
3
+ size 14244
checkpoint-788/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59fe5a4236e9c26c1ec5fc357163b1bb1f85829df5636d4415639339f5a213d2
3
+ size 1064
checkpoint-788/trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 788,
3
+ "best_metric": 0.7097524404525757,
4
+ "best_model_checkpoint": "siglip2-finetune-full/checkpoint-788",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 788,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 1.0,
14
+ "eval_accuracy": 0.788968253968254,
15
+ "eval_loss": 0.9223098158836365,
16
+ "eval_model_preparation_time": 0.007,
17
+ "eval_runtime": 160.6375,
18
+ "eval_samples_per_second": 78.437,
19
+ "eval_steps_per_second": 9.805,
20
+ "step": 394
21
+ },
22
+ {
23
+ "epoch": 1.2690355329949239,
24
+ "grad_norm": 53.61518478393555,
25
+ "learning_rate": 7.804878048780488e-07,
26
+ "loss": 1.4978,
27
+ "step": 500
28
+ },
29
+ {
30
+ "epoch": 2.0,
31
+ "eval_accuracy": 0.8326984126984127,
32
+ "eval_loss": 0.7097524404525757,
33
+ "eval_model_preparation_time": 0.007,
34
+ "eval_runtime": 160.8529,
35
+ "eval_samples_per_second": 78.332,
36
+ "eval_steps_per_second": 9.792,
37
+ "step": 788
38
+ }
39
+ ],
40
+ "logging_steps": 500,
41
+ "max_steps": 788,
42
+ "num_input_tokens_seen": 0,
43
+ "num_train_epochs": 2,
44
+ "save_steps": 500,
45
+ "stateful_callbacks": {
46
+ "TrainerControl": {
47
+ "args": {
48
+ "should_epoch_stop": false,
49
+ "should_evaluate": false,
50
+ "should_log": false,
51
+ "should_save": true,
52
+ "should_training_stop": true
53
+ },
54
+ "attributes": {}
55
+ }
56
+ },
57
+ "total_flos": 2.1108660247535616e+18,
58
+ "train_batch_size": 32,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
checkpoint-788/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6accd8d14522454c70031a1ac819cad32d4e338136bd21a2a4dcb3fdb03364bb
3
+ size 5304
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SiglipForImageClassification"
4
+ ],
5
+ "id2label": {
6
+ "0": "calling",
7
+ "1": "clapping",
8
+ "2": "cycling",
9
+ "3": "dancing",
10
+ "4": "drinking",
11
+ "5": "eating",
12
+ "6": "fighting",
13
+ "7": "hugging",
14
+ "8": "laughing",
15
+ "9": "listening_to_music",
16
+ "10": "running",
17
+ "11": "sitting",
18
+ "12": "sleeping",
19
+ "13": "texting",
20
+ "14": "using_laptop"
21
+ },
22
+ "initializer_factor": 1.0,
23
+ "label2id": {
24
+ "calling": 0,
25
+ "clapping": 1,
26
+ "cycling": 2,
27
+ "dancing": 3,
28
+ "drinking": 4,
29
+ "eating": 5,
30
+ "fighting": 6,
31
+ "hugging": 7,
32
+ "laughing": 8,
33
+ "listening_to_music": 9,
34
+ "running": 10,
35
+ "sitting": 11,
36
+ "sleeping": 12,
37
+ "texting": 13,
38
+ "using_laptop": 14
39
+ },
40
+ "model_type": "siglip",
41
+ "problem_type": "single_label_classification",
42
+ "text_config": {
43
+ "attention_dropout": 0.0,
44
+ "hidden_act": "gelu_pytorch_tanh",
45
+ "hidden_size": 768,
46
+ "intermediate_size": 3072,
47
+ "layer_norm_eps": 1e-06,
48
+ "max_position_embeddings": 64,
49
+ "model_type": "siglip_text_model",
50
+ "num_attention_heads": 12,
51
+ "num_hidden_layers": 12,
52
+ "projection_size": 768,
53
+ "torch_dtype": "float32",
54
+ "vocab_size": 256000
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.50.3",
58
+ "vision_config": {
59
+ "attention_dropout": 0.0,
60
+ "hidden_act": "gelu_pytorch_tanh",
61
+ "hidden_size": 768,
62
+ "image_size": 224,
63
+ "intermediate_size": 3072,
64
+ "layer_norm_eps": 1e-06,
65
+ "model_type": "siglip_vision_model",
66
+ "num_attention_heads": 12,
67
+ "num_channels": 3,
68
+ "num_hidden_layers": 12,
69
+ "patch_size": 16,
70
+ "torch_dtype": "float32"
71
+ }
72
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e2b9d5be40e7e84d93cbe40bf0b2b67d36503aa45faab3593811c712c53f649
3
+ size 371607988
preprocessor_config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_convert_rgb": null,
3
+ "do_normalize": true,
4
+ "do_rescale": true,
5
+ "do_resize": true,
6
+ "image_mean": [
7
+ 0.5,
8
+ 0.5,
9
+ 0.5
10
+ ],
11
+ "image_processor_type": "SiglipImageProcessor",
12
+ "image_std": [
13
+ 0.5,
14
+ 0.5,
15
+ 0.5
16
+ ],
17
+ "processor_class": "SiglipProcessor",
18
+ "resample": 2,
19
+ "rescale_factor": 0.00392156862745098,
20
+ "size": {
21
+ "height": 224,
22
+ "width": 224
23
+ }
24
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6accd8d14522454c70031a1ac819cad32d4e338136bd21a2a4dcb3fdb03364bb
3
+ size 5304